Implementing Convex Optimization in R: Two Econometric Examples

TL;DR

This paper demonstrates how convex optimization techniques, implemented in R with MOSEK, can efficiently estimate high-dimensional econometric models, improving speed and reliability across platforms.

Contribution

It extends previous work by integrating MOSEK with R for faster, reliable convex optimization in high-dimensional econometrics, with practical examples.

Findings

Faster estimation of high-dimensional models using R and MOSEK.

Convex optimization in R achieves comparable accuracy to existing methods.

Robust performance demonstrated across different computing platforms.

Abstract

Economists specify high-dimensional models to address heterogeneity in empirical studies with complex big data. Estimation of these models calls for optimization techniques to handle a large number of parameters. Convex problems can be effectively executed in modern statistical programming languages. We complement Koenker and Mizera (2014)'s work on numerical implementation of convex optimization, with focus on high-dimensional econometric estimators. Combining R and the convex solver MOSEK achieves faster speed and equivalent accuracy, demonstrated by examples from Su, Shi, and Phillips (2016) and Shi (2016). Robust performance of convex optimization is witnessed cross platforms. The convenience and reliability of convex optimization in R make it easy to turn new ideas into prototypes.